First the data is gathered from the different websites.
library(RCurl)
library(jsonlite)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(here)here() starts at /Users/AK/Library/Mobile Documents/com~apple~CloudDocs/Skrivebord/STUDIE/3. studieår/R for Bio Data Science/group_03_project# Create 'data' directory if it doesn't exist
if (!dir.exists(here("data"))) {dir.create(here("data")) }
# Create 'raw' directory if it doesn't exist
if (!dir.exists(here("data/_raw"))) {dir.create(here("data/_raw")) }# Fetch dataset
url <-
"https://archive.ics.uci.edu/ml/machine-learning-databases/00296/dataset_diabetes.zip"
temp <- tempfile()
download.file(url, temp)
# Unzip files directly into the 'data' directory
unzip(temp, exdir = here("data"))
# The data lies in a subfolder, whichi we would like to remove
path_a <- file.path(here("data"), "dataset_diabetes")
path_b <- file.path(here("data"), "_raw")
# Get the list of files with their full paths from 'path_a'
my_files <- list.files(path_a, full.names = TRUE)
# Copy files to 'path_b'
file.copy(from = my_files, to = path_b, overwrite = TRUE)[1] TRUE TRUE# Delete the now-empty folder
unlink(path_a, recursive = TRUE)# Fetch data
url_ICD9 <- "https://www.cms.gov/medicare/coding/icd9providerdiagnosticcodes/downloads/icd-9-cm-v32-master-descriptions.zip"
temp <- tempfile()
download.file(url_ICD9, temp)
# Unzip files directly into the '_raw' directory
unzip(temp, exdir = here("data/_raw"))
# The zip-folder also contains data on surgaries, which is not relevent here. The unused files are removed
unlink(here("data/_raw/CMS32_DESC_LONG_SG.txt"))
unlink(here("data/_raw/CMS32_DESC_SHORT_SG.txt"))
unlink(here("data/_raw/CMS32_DESC_LONG_SHORT_SG.xlSX"))
unlink(here("data/_raw/CMS32_DESC_LONG_SHORT_DX.xlsx"))The four different files are then combined, and different types of NA values are combined.
suppressWarnings({
library("tidyverse")
library("here")
library("broom")
})suppressWarnings({
#Data is loaded without defined column names
meta_data <- read_csv(here("data/_raw/IDs_mapping.csv"),
na = "",
col_names = c("type_id", "description"),
show_col_types = FALSE)
# Remove NA columns and add a column based on admission type, that is numeric. The NA values in this, will be the names of the type of metadata the id describes. Also adds a meta_type column, which has the type in the cells that are NAs in the numeric type_id_as_num
meta_data <- meta_data |>
na.omit() |>
mutate(type_id,
type_id_as_num = as.numeric(type_id)) |>
mutate(meta_type = ifelse(is.na(type_id_as_num),
type_id,
NA))
#Fills meta_type with the last non-NA cell
meta_data <- meta_data |>
fill(meta_type)
#Removes the rows containing the names, drops admission_type_is_as_num
meta_data_clean <- meta_data |>
filter(!is.na(type_id_as_num)) |>
select(!type_id) |>
rename(type_id = type_id_as_num)
})
admission_type <- meta_data_clean |>
filter(meta_type == "admission_type_id") |>
select(-meta_type) |>
mutate(description = case_when(description %in% c("NULL", "Not Mapped", "Not Available") ~ NA,
TRUE ~ description))
discharge_disposition <- meta_data_clean |>
filter(meta_type == "discharge_disposition_id") |>
select(-meta_type) |>
mutate(description = case_when(description %in% c("NULL", "Not Mapped", "Unknown/Invalid") ~ NA,
TRUE ~ description))
admission_source <- meta_data_clean |>
filter(meta_type == "admission_source_id") |>
select(-meta_type) |>
mutate(description = case_when(description %in% c("NULL", "Not Mapped", "Unknown/Invalid", "Not Available") ~ NA,
TRUE ~ description))The data is downloaded here as the newest version from 2014:
ICD-9-CM Diagnosis and Procedure Codes: Abbreviated and Full Code Titles | CMS
From the files the short and long ds are chosen (sg are surgical and dx are diagnoses).
When running the 01_load.qmd, all the relevant files should be downloaded and placed in data/_raw
# First the data will be loaded into a dataframe of one column
ICD9_short <- read_delim(here("data/_raw/CMS32_DESC_SHORT_DX.txt"),
col_names = "data",
show_col_types = FALSE,
delim = "\n")
ICD9_long <- read_delim(here("data/_raw/CMS32_DESC_LONG_DX.txt"),
col_names = "data",
show_col_types = FALSE,
delim = "\n")
#The long dataset includes é and è in for example Ménière's disease. To deal with this, the data is converted to UTF-8
ICD9_long <- ICD9_long |>
mutate(data = iconv(data,
from = "latin1",
to = "UTF-8",
sub = "byte"))
# The first value in each row is the ID, but the delimiter is not preserved. Each row is therefore split at the first, and everything else is merged into the second column:
ICD9_short <- ICD9_short |>
separate(col = data,
into = c("ID", "Description_short"),
extra = "merge")
ICD9_long <- ICD9_long |>
separate(col = data,
into = c("ID", "Description_long"),
extra = "merge")
# The long and short dataframe, should have identical IDs, however in case there are some differences, we want all data, and therefore use full_join
ICD9 <- full_join(ICD9_short,
ICD9_long,
by = "ID")
suppressWarnings({
ICD9 <- ICD9 |>
mutate(ID = ifelse(str_starts(ID, "[VE]"),
ID,
as.double(str_c(substr(ID,1,3),
".",
substr(ID,4,length(ID))))))
})diabetes_data <- read_csv(here("data/_raw/diabetic_data.csv"),
na = c("?", "None"),
show_col_types = FALSE)
#Change NO in readmitted column to No
diabetes_data <- diabetes_data |>
mutate(readmitted,
readmitted = str_replace(string = readmitted,
"NO",
"No"))
#Change Ch in change column to Yes
diabetes_data <- diabetes_data |>
mutate(change,
change = str_replace(string = change,
"Ch",
"Yes"))full_data <- diabetes_data |>
left_join(admission_type,
join_by('admission_type_id' == 'type_id'),
relationship = "many-to-one") |>
rename(admission_type = description) |>
relocate(admission_type, .after = admission_type_id) |>
select(-admission_type_id)
full_data <- full_data |>
left_join(admission_source,
join_by('admission_source_id' == 'type_id'),
relationship = "many-to-one") |>
rename(admission_source = description) |>
relocate(admission_source, .after = admission_source_id) |>
select(-admission_source_id)
full_data <- full_data |>
left_join(discharge_disposition,
join_by('discharge_disposition_id' == 'type_id'),
relationship = "many-to-one") |>
rename(discharge_disposition = description) |>
relocate(discharge_disposition, .after = discharge_disposition_id) |>
select(-discharge_disposition_id)full_data <- full_data |>
left_join(ICD9,
join_by('diag_1' == 'ID'),
relationship = "many-to-one",
na_matches = "never") |>
rename(diag_1_short = Description_short,
diag_1_long = Description_long) |>
mutate(diag_1_short = case_when(is.na(diag_1_short) ~ diag_1,
!is.na(diag_1_short) ~ diag_1_short)) |>
mutate(diag_1_long = case_when(is.na(diag_1_long) ~ diag_1,
!is.na(diag_1_long) ~ diag_1_long))
full_data <- full_data |>
left_join(ICD9,
join_by('diag_2' == 'ID'),
relationship = "many-to-one",
na_matches = "never") |>
rename(diag_2_short = Description_short,
diag_2_long = Description_long)|>
mutate(diag_2_short = case_when(is.na(diag_2_short) ~ diag_2,
!is.na(diag_2_short) ~ diag_2_short)) |>
mutate(diag_2_long = case_when(is.na(diag_2_long) ~ diag_2,
!is.na(diag_2_long) ~ diag_2_long))
full_data <- full_data |>
left_join(ICD9,
join_by('diag_3' == 'ID'),
relationship = "many-to-one",
na_matches = "never") |>
rename(diag_3_short = Description_short,
diag_3_long = Description_long)|>
mutate(diag_3_short = case_when(is.na(diag_3_short) ~ diag_3,
!is.na(diag_3_short) ~ diag_3_short)) |>
mutate(diag_3_long = case_when(is.na(diag_3_long) ~ diag_3,
!is.na(diag_3_long) ~ diag_3_long))
full_data <- full_data |>
relocate(c(diag_1_short,
diag_2_short,
diag_3_short,
diag_1_long,
diag_2_long,
diag_3_long), .after = diag_1) |>
select(-diag_1, -diag_2, -diag_3)write_csv(full_data, here("data/02_dat_clean.csv"))Two columns are created, one for the amount of encounters per patient and one for the total amount of days the patient has spend in the hospital within the dataset.
library("here")
library("tidyverse")clean_data <- read_csv(here("data/02_dat_clean.csv")) Rows: 101766 Columns: 53
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (43): race, gender, age, weight, admission_type, discharge_disposition, ...
dbl (10): encounter_id, patient_nbr, time_in_hospital, num_lab_procedures, n...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Add columns that signifies the amount of encounters one patient has in the data set.
clean_data <- clean_data |>
count(patient_nbr) |>
right_join(clean_data,
join_by(patient_nbr)) |>
rename("nr_encounters" = n) |>
relocate(c(patient_nbr, nr_encounters),
.after = encounter_id)Add column for total amount of days spent in hospital
clean_data <- clean_data |>
group_by(patient_nbr) |>
summarise(sum(time_in_hospital)) |>
right_join(clean_data,
join_by(patient_nbr)) |>
rename("total_time_hospital" = "sum(time_in_hospital)") |>
relocate(total_time_hospital,
.after = time_in_hospital)clean_data <- clean_data |>
relocate(patient_nbr,
.after = encounter_id)
write_csv(clean_data, here("data/03_dat_aug.csv"))
write_csv(clean_data, here("R/Shiny_app/03_dat_aug.csv"))Different key statistics of the data are found.
library("here")
library("tidyverse")aug_data <- read_csv(here("data/03_dat_aug.csv")) Rows: 101766 Columns: 55
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (43): race, gender, age, weight, admission_type, discharge_disposition, ...
dbl (12): encounter_id, patient_nbr, nr_encounters, time_in_hospital, total_...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.aug_data |>
select(encounter_id) |>
count()# A tibble: 1 × 1
n
<int>
1 101766aug_data |>
distinct(patient_nbr) |>
count()# A tibble: 1 × 1
n
<int>
1 71518max_time <- aug_data |>
summarise(max(total_time_hospital)) |>
pull()
aug_data |>
distinct(patient_nbr, total_time_hospital) |>
filter(total_time_hospital == max_time)# A tibble: 1 × 2
patient_nbr total_time_hospital
<dbl> <dbl>
1 84428613 180max_enc <- aug_data |>
summarise(max(nr_encounters)) |>
pull()
aug_data |>
distinct(patient_nbr, nr_encounters) |>
filter(nr_encounters == max_enc)# A tibble: 1 × 2
patient_nbr nr_encounters
<dbl> <dbl>
1 88785891 40max_med <- aug_data |>
summarise(max(num_medications)) |>
pull()
aug_data |>
distinct(patient_nbr, num_medications) |>
filter(num_medications == max_med)# A tibble: 1 × 2
patient_nbr num_medications
<dbl> <dbl>
1 24189597 81max_dia <- aug_data |>
summarise(max(number_diagnoses)) |>
pull()
aug_data |>
distinct(patient_nbr, number_diagnoses) |>
filter(number_diagnoses == max_dia)# A tibble: 45 × 2
patient_nbr number_diagnoses
<dbl> <dbl>
1 30577455 16
2 31059126 16
3 37748088 16
4 38158101 16
5 40595031 16
6 40634091 16
7 40851090 16
8 41015448 16
9 41164047 16
10 41306769 16
# ℹ 35 more rowsaug_data |>
group_by(age) |>
count()# A tibble: 10 × 2
# Groups: age [10]
age n
<chr> <int>
1 [0-10) 161
2 [10-20) 691
3 [20-30) 1657
4 [30-40) 3775
5 [40-50) 9685
6 [50-60) 17256
7 [60-70) 22483
8 [70-80) 26068
9 [80-90) 17197
10 [90-100) 2793aug_data |>
distinct(patient_nbr, gender) |>
group_by(gender) |>
count()# A tibble: 3 × 2
# Groups: gender [3]
gender n
<chr> <int>
1 Female 38026
2 Male 33492
3 Unknown/Invalid 3aug_data |>
distinct(patient_nbr, race) |>
group_by(race) |>
count()# A tibble: 6 × 2
# Groups: race [6]
race n
<chr> <int>
1 AfricanAmerican 12932
2 Asian 517
3 Caucasian 53601
4 Hispanic 1534
5 Other 1209
6 <NA> 1977The data is visualized to discover trends.
library(tidyverse)
library(here)data <- read.csv(here("data/03_dat_aug.csv"))data |>
group_by(age, gender) |>
summarise(average_diagnoses = mean(number_diagnoses), .groups = "drop") |>
ggplot(aes(x = age,
y = average_diagnoses,
fill = gender)) +
geom_col(position = "dodge") +
labs(x = "Age Group",
y = "Average number of diagnoses",
fill = "Gender",
title = "Average number of diagnoses for all age groups and genders per encounter") +
scale_fill_manual(values=c('hotpink',
'cornflowerblue',
'grey35')) 
data |>
mutate(race = ifelse(is.na(race),'Other',race)) |>
mutate(race = ifelse(race == 'Other', 'Other/Unspecified', race)) |>
group_by(age,
gender,
race) |>
summarize(average_diagnoses = mean(number_diagnoses), .groups = "drop") |>
ggplot(mapping = aes(x = age,
y = average_diagnoses,
fill = gender)) +
geom_col(position = "dodge",
alpha = 1.0) +
facet_wrap(~ race) +
labs(
x = "Age Group",
y = "Average number of diagnoses",
fill = "Gender",
title =
"Average number of diagnoses for all age groups and genders,\nfacet wrapped for race") +
scale_fill_manual(values=c('hotpink',
'cornflowerblue',
'grey35')) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 60, hjust =1),
legend.position = 'inside',
legend.position.inside = c(0.85,0.15))
data |>
select(patient_nbr, race, gender) |>
distinct(patient_nbr, .keep_all = TRUE) |>
mutate(race = ifelse(is.na(race), "Other", race)) |>
group_by(race, gender) |>
summarise(count = n(), .groups = "drop") |>
mutate(text_color = ifelse(count > 4000, "white",
ifelse(gender == "Female", "hotpink",
ifelse(gender == "Male", "cornflowerblue", "grey35")))) |>
ggplot(aes(x = race, y = count, fill = gender)) +
geom_bar(stat = "identity", position = "stack") +
geom_text(
aes(label = count, color = text_color),
data = data |>
select(patient_nbr, race, gender) |>
distinct(patient_nbr, .keep_all = TRUE) |>
mutate(race = ifelse(is.na(race), "Other", race)) |>
group_by(race, gender) |>
summarise(count = n(), .groups = "drop") |>
filter(count > 4000) |>
mutate(text_color = ifelse(count > 4000, "white",
ifelse(gender == "Female", "hotpink",
ifelse(gender == "Male", "cornflowerblue", "grey35")))),
position = position_stack(vjust = 0.5),
size = 4
) +
geom_text(
aes(label = count, color = text_color),
data = data |>
select(patient_nbr, race, gender) |>
distinct(patient_nbr, .keep_all = TRUE) |>
mutate(race = ifelse(is.na(race), "Other", race)) |>
group_by(race, gender) |>
summarise(count = n(), .groups = "drop") |>
filter(count <= 4000) |>
mutate(text_color = ifelse(count > 4000, "white",
ifelse(gender == "Female", "hotpink",
ifelse(gender == "Male", "cornflowerblue", "grey35")))),
position = position_dodge2(width = 0.8),
size = 4,
vjust = -3
) +
scale_color_identity() +
labs(
x = "Race",
y = "Count",
fill = "Gender",
title = str_c("Gender/race distribution of dataset, total no. of patients: ",
data |>
select(patient_nbr) |>
group_by(patient_nbr) |>
summarise(count = n()) |>
count()
)
) +
scale_fill_manual(values = c("hotpink", "cornflowerblue", "grey35")) +
theme_minimal() +
theme(legend.position = "bottom")
#Finding the 8 most frequent discharge disposition for any admission type
top_8_discharge_dispositions <- data |>
group_by(discharge_disposition)|>
summarize(n = n()) |> #Summarizing the total amount of occurences of each discharge type
arrange(desc(n)) |> #Arranging from high -> low
head(8) |>
select(discharge_disposition) |>
pull() #Converting into a vector
data |>
select(discharge_disposition, age) |>
filter(discharge_disposition %in% top_8_discharge_dispositions) |> #Filtering for only the cases where the discharge type was in the top 8
group_by(discharge_disposition, age) |>
summarize(n = n(),.groups = 'keep') |>
drop_na(discharge_disposition) |>
ggplot(
mapping = aes(x = discharge_disposition,
y = n,
fill = age)
) +
geom_col(position = "dodge") +
scale_fill_viridis_d(option = "viridis") +
scale_x_discrete(labels = function(x) str_wrap(x, width = 35)) +
labs(
x = "Discharge disposition",
y = "Count",
fill = "Age group",
title = "Discharge disposition for all age groups for all admission types"
) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 60, hjust =1)
)
#Finding the top 8 for the casses related to emergency admissions only
top_8_discharge_dispositions <- data |>
filter(admission_type == "Emergency") |>
group_by(discharge_disposition)|>
summarize(n = n()) |>
arrange(desc(n)) |>
head(8) |>
select(discharge_disposition) |>
pull()
data |>
filter(admission_type == "Emergency") |>
select(discharge_disposition, age) |>
filter(discharge_disposition %in% top_8_discharge_dispositions) |>
group_by(discharge_disposition, age) |>
summarize(n = n(),.groups = 'keep') |>
drop_na(discharge_disposition) |>
ggplot(
mapping = aes(x = discharge_disposition,
y = n,
fill = age)
) +
geom_col(position = "dodge") +
scale_fill_viridis_d(option = "viridis") +
scale_x_discrete(labels = function(x) str_wrap(x, width = 35)) +
labs(
x = "Discharge disposition",
y = "Count",
fill = "Age group",
title = "Discharge disposition for all age groups for emergency admissions"
) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 60, hjust =1)
)
top_8_discharge_dispositions <- data |>
filter(admission_type == "Urgent") |>
group_by(discharge_disposition)|>
summarize(n = n()) |>
arrange(desc(n)) |>
head(8) |>
select(discharge_disposition) |>
pull()
data |>
filter(admission_type == "Urgent") |>
select(discharge_disposition, age) |>
filter(discharge_disposition %in% top_8_discharge_dispositions) |>
group_by(discharge_disposition, age) |>
summarize(n = n(),.groups = 'keep') |>
drop_na(discharge_disposition) |>
ggplot(
mapping = aes(x = discharge_disposition,
y = n,
fill = age)
) +
geom_col(position = "dodge") +
scale_fill_viridis_d(option = "viridis") +
scale_x_discrete(labels = function(x) str_wrap(x, width = 35)) +
labs(
x = "Discharge disposition",
y = "Count",
fill = "Age group",
title = "Discharge disposition for all age groups for urgent admissions"
) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 60, hjust =1)
)
top_8_discharge_dispositions <- data |>
filter(admission_type == "Elective") |>
group_by(discharge_disposition)|>
summarize(n = n()) |>
arrange(desc(n)) |>
head(8) |>
select(discharge_disposition) |>
pull()
data |>
filter(admission_type == "Elective") |>
select(discharge_disposition, age) |>
filter(discharge_disposition %in% top_8_discharge_dispositions) |>
group_by(discharge_disposition, age) |>
summarize(n = n(),.groups = 'keep') |>
drop_na(discharge_disposition) |>
ggplot(
mapping = aes(x = discharge_disposition,
y = n,
fill = age)
) +
geom_col(position = "dodge") +
scale_fill_viridis_d(option = "viridis") +
scale_x_discrete(labels = function(x) str_wrap(x, width = 35)) +
labs(
x = "Discharge disposition",
y = "Count",
fill = "Age group",
title = "Discharge disposition for all age groups for elective admissions"
) +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 60, hjust =1)
)
data |>
select(patient_nbr,gender) |>
group_by(patient_nbr) |>
mutate(number_of_visits = n()) |>
distinct(patient_nbr,.keep_all = TRUE) |>
ungroup() |>
select(gender, number_of_visits) |>
group_by(number_of_visits,gender) |>
summarise(count = n(), .groups = 'drop') |>
ggplot(aes(x = number_of_visits, y = gender)) +
geom_count(aes(color = gender,
size = count,
shape = factor(count)),
position = position_jitter(height = 0.2)) +
labs(x = "Number of visits",
y = "Gender",
title = "Number of visits by gender") +
scale_color_manual(values = c("hotpink", "cornflowerblue", "grey35")) +
scale_size_continuous(
range = c(2, 10),
trans = 'sqrt',
breaks = c(1, 5, 100, 1000, 10000, 20000),
labels = c('1', '5', '100', '1000', '10000', '20000+')) +
scale_shape_manual(values=c(17,rep(16, 28))) +
theme_minimal() +
theme(legend.position = 'bottom',
legend.justification = "center") +
guides( color = guide_none(),
size = guide_legend(title = "Counts",
override.aes = list(shape = c(17,rep(16,5))),
ncol = 6),
shape = guide_none()) +
coord_flip()
data |>
filter(nr_encounters == 1) |>
select(patient_nbr, number_diagnoses, gender) |>
group_by(patient_nbr) |>
mutate(visit_num = row_number()) |>
ungroup() |>
pivot_wider(
names_from = visit_num,
values_from = number_diagnoses,
names_prefix = "visit_",
values_fill = list(number_diagnoses = NA)) |>
ggplot(aes(x=visit_1,fill=gender)) +
geom_boxplot() +
labs(title = 'Amount of diagnoses for people with only 1 visit',
x ='Number of diagnoses',
fill = 'Gender') +
scale_fill_manual(values=c('hotpink',
'cornflowerblue',
'grey35')) 
data |>
filter(nr_encounters == 2) |>
select(patient_nbr, number_diagnoses,encounter_id) |>
group_by(patient_nbr) |>
arrange(encounter_id, .by_group = TRUE) |>
mutate(visit_num = row_number()) |>
ungroup() |>
select(-encounter_id) |>
pivot_wider(
names_from = visit_num,
values_from = number_diagnoses,
names_prefix = "visit_",
values_fill = list(number_diagnoses = NA)) |>
pivot_longer(cols = -patient_nbr,
names_to = 'visit') |>
ggplot(aes(x=value,fill=visit)) +
geom_boxplot() +
labs(title = str_c('Amount of diagnoses for people with 2 visits (',
data |>
filter(nr_encounters == 2) |>
pull(patient_nbr) |>
unique() |>
length(),
' people)'),
x ='Number of diagnoses',
fill = 'Visit number') +
scale_fill_manual(
values = c("visit_1" = "lightblue3", "visit_2" = "seagreen3"),
labels = c("1", "2")
)
data |>
filter(nr_encounters == 3) |>
select(patient_nbr, number_diagnoses, encounter_id) |>
group_by(patient_nbr) |>
arrange(encounter_id, .by_group = TRUE) |>
mutate(visit_num = row_number()) |>
ungroup() |>
select(-encounter_id) |>
pivot_wider(
names_from = visit_num,
values_from = number_diagnoses,
names_prefix = "visit_",
values_fill = list(number_diagnoses = NA)) |>
pivot_longer(cols = -patient_nbr,
names_to = 'visit') |>
ggplot(aes(x=value,fill=visit)) +
geom_boxplot() +
labs(title = str_c('Amount of diagnoses for people with 3 visits (',
data |>
filter(nr_encounters == 3) |>
pull(patient_nbr) |>
unique() |>
length(),
' people)'),
x ='Number of diagnoses',
fill = 'Visit number') +
scale_fill_manual(
values = c("visit_1" = "lightblue3", "visit_2" = "seagreen3","visit_3" = 'darkolivegreen'),
labels = c("1", "2","3")
)
data |>
select(patient_nbr, number_diagnoses,encounter_id) |>
group_by(patient_nbr) |>
arrange(encounter_id, .by_group = TRUE) |>
mutate(visit_num = row_number()) |>
ungroup() |>
select(-encounter_id) |>
pivot_wider(
names_from = visit_num,
values_from = number_diagnoses,
names_prefix = "visit_",
values_fill = list(number_diagnoses = NA)) |>
pivot_longer(cols = c(-patient_nbr),
names_to = 'visit',
values_to = 'diagnosis') |>
drop_na(diagnosis) |>
group_by(visit) |>
summarise(mean_diagnosis = mean(diagnosis), no_people = n()) |>
mutate(visit = str_extract(visit, "\\d+"),
visit = factor(visit,levels=sort(as.numeric(visit)))) |>
ggplot(aes(x=visit,y=mean_diagnosis)) +
geom_point(aes(color=no_people),size=3) +
scale_color_gradient2(low='hotpink',
mid='orange',
high='cornflowerblue',
midpoint=12000,
limits=c(2,NA),
n.breaks=5,
transform = 'sqrt',
na.value = 'forestgreen',
guide = guide_colorbar(title = "Amount of people")
) +
theme_minimal() +
theme(axis.text.x=element_text(angle=90,hjust=1)) +
labs(title = 'Average number of diagnoses per visit by patient',
subtitle = '- Green dots signify 1 person',
x = 'Number of visit by patients',
y = 'Average number of diagnoses') 
data |>
select(patient_nbr, encounter_id, nr_encounters, diag_1_long) |>
group_by(diagnosis = diag_1_long) |>
summarise(count = n(), .groups = "drop") |>
top_n(10, count) |>
inner_join(data, by = c("diagnosis" = "diag_1_long")) |>
group_by(nr_encounters, diagnosis) |>
summarise(diagnosis_count = n(), .groups = "drop") |>
ggplot(aes(x = nr_encounters, y = diagnosis, fill = diagnosis_count)) +
geom_tile(color = "white") +
scale_fill_gradient(low = "orange", high = "purple") +
scale_y_discrete(labels = function(y) str_wrap(y, width = 45)) +
labs(
x = "Number of visits",
y = "",
fill = "Amount of patients",
title = "Top 10 most common primary diagnosis per visit"
) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 0, hjust = 1),
legend.position = 'bottom',
legend.background = element_rect(linewidth = 0.5, color = 'grey'),
legend.text = element_text(angle=20,hjust=1),
legend.justification = 'left',
legend.title.position = 'top',
plot.title = element_text(hjust = -3))
data |>
group_by(patient_nbr) |>
filter(n_distinct(gender) > 1) |>
arrange(encounter_id, .by_group = TRUE)# A tibble: 7 × 55
# Groups: patient_nbr [3]
encounter_id patient_nbr nr_encounters race gender age weight
<int> <int> <int> <chr> <chr> <chr> <chr>
1 220872936 40867677 3 <NA> Male [40-50) <NA>
2 232356060 40867677 3 <NA> Female [40-50) <NA>
3 291975978 40867677 3 <NA> Male [40-50) <NA>
4 20729328 55500588 2 Caucasian Female [70-80) <NA>
5 96312942 55500588 2 Caucasian Male [80-90) <NA>
6 183845022 109210482 2 Caucasian Female [50-60) <NA>
7 186533256 109210482 2 Caucasian Male [50-60) <NA>
# ℹ 48 more variables: admission_type <chr>, discharge_disposition <chr>,
# admission_source <chr>, time_in_hospital <int>, total_time_hospital <int>,
# payer_code <chr>, medical_specialty <chr>, num_lab_procedures <int>,
# num_procedures <int>, num_medications <int>, number_outpatient <int>,
# number_emergency <int>, number_inpatient <int>, diag_1_short <chr>,
# diag_2_short <chr>, diag_3_short <chr>, diag_1_long <chr>,
# diag_2_long <chr>, diag_3_long <chr>, number_diagnoses <int>, …diabetes_count <- data |>
select(patient_nbr,ends_with('_long')) |>
pivot_longer(cols = ends_with('_long'),
values_to = 'all_diagnoses',
names_to = 'diag_order') |>
select(-diag_order) |>
group_by(patient_nbr) |>
filter(str_detect(all_diagnoses,'iabetes')) |>
distinct() |>
group_by(all_diagnoses) |>
summarise(count=n()) diabetes_count |>
mutate(type = ifelse(str_detect(all_diagnoses,'type I '),'Type I','Type II or unspecified'),
uncontrolled = ifelse(str_detect(all_diagnoses,', uncontrolled'),
'Uncontrolled', 'Not specified as uncontrolled'),
no_complication = ifelse(str_detect(all_diagnoses, 'without mention of complication'),
'No complication','Complications')) |>
mutate(complication_type = ifelse(no_complication == 'Complications',
str_to_sentence(str_extract(all_diagnoses,'(?<=with ).*(?=, *type)')),
'None')) |>
mutate(complication_type = ifelse(is.na(complication_type),'Pregnancy complications',complication_type)) |>
mutate(complication_type = factor(complication_type,
levels = c(unique(complication_type[complication_type != 'None']), 'None'))) |>
ggplot(aes(x = uncontrolled, y=count, fill = complication_type)) +
geom_bar(stat='identity',) +
facet_wrap(~type) +
labs(title = 'Diabetes managment and complications',
subtitle = str_c('For patients with diabetes as primary or secondary diagnosis (',
sum(diabetes_count$count),' patients)'),
x = 'Controllation of disease',
y = 'Number of instances',
fill = 'Complications') +
theme_minimal() +
scale_x_discrete(labels = function(x) str_wrap(x,width = 17)) +
scale_fill_viridis_d(option = 'viridis',direction=-1) 
diabetes_count |>
mutate(type = ifelse(str_detect(all_diagnoses,'type I '),'Type I','Type II or unspecified'),
uncontrolled = ifelse(str_detect(all_diagnoses,', uncontrolled'),
'Uncontrolled', 'Not specified as uncontrolled'),
no_complication = ifelse(str_detect(all_diagnoses, 'without mention of complication'),
'No complication','Complications')) |>
mutate(complication_type = ifelse(no_complication == 'Complications',
str_to_sentence(str_extract(all_diagnoses,'(?<=with ).*(?=, *type)')),
'None')) |>
mutate(complication_type = ifelse(is.na(complication_type),'Pregnancy complications',complication_type)) |>
filter(!complication_type == 'None') |>
ggplot(aes(x = uncontrolled, y=count, fill = complication_type)) +
geom_bar(stat='identity',) +
facet_wrap(~type) +
labs(title = 'Diabetes managment and complications',
subtitle = str_c(
'For patients with diabetes as primary or secondary diagnosis\n(only for cases with complications: ',
diabetes_count |>
filter(!str_detect(all_diagnoses,
'without mention of complication')) |>
select(count) |>
sum(),
' patients)'),
x = 'Controllation of disease',
y = 'Number of instances',
fill = 'Complications') +
theme_minimal() +
scale_fill_viridis_d(option = 'plasma',direction=-1) +
scale_x_discrete(labels = function(x) str_wrap(x,width = 17))
A PCA is conducted.
library(tidyverse)
library(broom)
library(cowplot)
library(ggplot2)
library(here)
aug_data <- read_csv(here("data/03_dat_aug.csv"))Looking at the data in PC coordinates:
numeric_data <- aug_data |>
select(where(is.numeric)) |>
na.omit() |>
select(where(~ var(., na.rm = TRUE) > 0))
pca_fit <- numeric_data |>
prcomp(scale = TRUE)
data_clean <- aug_data |>
filter(row_number() %in% rownames(numeric_data))
pca_plot <- pca_fit |>
augment(data_clean) |>
ggplot(aes(.fittedPC1, .fittedPC2)) +
geom_point(size = 1.5) +
theme_half_open(12) +
background_grid()
pca_plot
Now we extract the rotation matrix
pca_fit |>
tidy(matrix = "rotation")# A tibble: 144 × 3
column PC value
<chr> <dbl> <dbl>
1 encounter_id 1 0.0920
2 encounter_id 2 -0.113
3 encounter_id 3 0.616
4 encounter_id 4 -0.00514
5 encounter_id 5 0.200
6 encounter_id 6 -0.0289
7 encounter_id 7 0.166
8 encounter_id 8 0.0607
9 encounter_id 9 0.504
10 encounter_id 10 -0.327
# ℹ 134 more rowsand plot it:
# arrow for plotting
arrow_style <- arrow(
angle = 20, ends = "first", type = "closed", length = grid::unit(8, "pt")
)
# rotation matrix
pca_fit |>
tidy(matrix = "rotation") |>
pivot_wider(names_from = "PC",
names_prefix = "PC",
values_from = "value") |>
ggplot(aes(PC1, PC2)) +
geom_segment(xend = 0,
yend = 0,
arrow = arrow_style) +
geom_text(
aes(label = column),
hjust = 1, nudge_x = -0.02,
color = "#904C2F"
) +
xlim(-1.25, .5) +
ylim(-.5, 1) +
coord_fixed() +
theme_minimal_hgrid(12)Warning: Removed 3 rows containing missing values or values outside the scale range
(`geom_segment()`).Warning: Removed 3 rows containing missing values or values outside the scale range
(`geom_text()`).
Look at the variance
pca_fit |>
tidy(matrix = "eigenvalues")# A tibble: 12 × 4
PC std.dev percent cumulative
<dbl> <dbl> <dbl> <dbl>
1 1 1.65 0.228 0.228
2 2 1.39 0.162 0.389
3 3 1.30 0.141 0.530
4 4 0.992 0.0820 0.612
5 5 0.973 0.0788 0.691
6 6 0.931 0.0723 0.763
7 7 0.854 0.0607 0.824
8 8 0.804 0.0538 0.877
9 9 0.721 0.0433 0.921
10 10 0.682 0.0387 0.959
11 11 0.647 0.0349 0.994
12 12 0.262 0.00572 1 And now the plot:
pca_bar_plot <- pca_fit |>
tidy(matrix = "eigenvalues") |>
ggplot(aes(PC, percent)) +
geom_col(fill = "#56B4E9",
alpha = 0.8) +
scale_x_continuous(breaks = 1:9) +
scale_y_continuous(
labels = scales::percent_format(),
expand = expansion(mult = c(0, 0.01))
) +
theme_minimal_hgrid(12)
pca_bar_plot
It is seen that 22.5% of the variance is explained by PC1. The drop of is after PC3.
ggsave(
filename = here("results", "06_pca_plot.png"),
plot = pca_plot,
width = 8,
height = 6,
dpi = 300
)
ggsave(
filename = here("results", "06_pca_bar_plot.png"),
plot = pca_bar_plot,
width = 8,
height = 6,
dpi = 300
)We can then extract what each Principle component is made up of:
# Extract the loadings
loadings <- pca_fit$rotation |>
as_tibble(rownames = "Variable")
print(loadings)# A tibble: 12 × 13
Variable PC1 PC2 PC3 PC4 PC5 PC6 PC7 PC8
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 encounter_id 0.0920 -0.113 0.616 -0.00514 0.200 -0.0289 0.166 0.0607
2 patient_nbr 0.0647 -0.124 0.604 -0.0877 0.151 -0.00526 0.332 0.148
3 nr_encounte… 0.507 0.283 -0.0516 0.0250 0.128 -0.143 0.0778 -0.0949
4 time_in_hos… 0.242 -0.429 -0.227 -0.174 -0.0544 -0.0330 -0.0464 0.635
5 total_time_… 0.537 0.136 -0.130 -0.0491 0.112 -0.187 0.0628 0.119
6 num_lab_pro… 0.134 -0.341 -0.126 -0.543 -0.278 0.279 0.404 -0.465
7 num_procedu… 0.0368 -0.385 -0.133 0.659 0.252 0.0222 0.187 -0.358
8 num_medicat… 0.221 -0.505 -0.107 0.215 0.0194 0.0150 0.0189 0.121
9 number_outp… 0.118 0.0191 0.214 0.335 -0.865 -0.260 0.0860 0.0233
10 number_emer… 0.233 0.157 0.118 0.218 -0.124 0.886 -0.164 0.152
11 number_inpa… 0.448 0.230 -0.0274 0.0124 0.0406 -0.0253 0.0706 -0.229
12 number_diag… 0.214 -0.303 0.281 -0.154 -0.0167 -0.102 -0.782 -0.335
# ℹ 4 more variables: PC9 <dbl>, PC10 <dbl>, PC11 <dbl>, PC12 <dbl>pca_data <- pca_fit |>
augment(data_clean)
pca_data <- pca_data |>
mutate(cluster = kmeans(select(pca_data, .fittedPC1:.fittedPC3), centers = 3)$cluster) |>
mutate(cluster = as.factor(cluster))
pca_clustered <- pca_data |>
ggplot(aes(x = .fittedPC1, y = .fittedPC2, color = cluster)) +
labs(x = "PC1",
y = "PC2",
title = "Clustering of patient groups based on PCA") +
geom_point() +
theme_minimal()
pca_clustered
ggsave(
filename = here("results", "06_pca_clustered.jpg"),
plot = pca_clustered ,
width = 8,
height = 6,
dpi = 300
)PC1: Likely represents overall patient interaction with the healthcare system.
PC2: Likely represents treatment intensity or complexity.
PC3: Likely represents inpatient care or hospitalization frequency.
A shiny app is created to discover correlation between readmission and medications.
library(“shiny”) # Load necessary scripts source(“ui.R”) source(“server.R”)
shinyApp(ui = ui, server = server)
library(shiny) df <- read.csv(“03_dat_aug.csv”)
ui <- fluidPage( titlePanel(“Diabetes Patient Readmissions”),
sidebarLayout( sidebarPanel( # File upload to load the data fileInput(“data_file”, “Upload Dataset”, accept = “.csv”),
# Filter for readmission status
selectInput(
"readmission_filter",
"Filter by Readmission Status:",
choices = c("All", unique(df$readmitted)),
selected = "All"
),
selectInput(
"age",
"Filter by age group:",
choices = c("All", sort(unique(df$age))),
selected = "All"
),
selectInput(
"race",
"Filter by race:",
choices = c("All", sort(unique(df$race))),
selected = "All"
),
selectInput(
"gender",
"Filter by gender",
choices = c("All", sort(unique(df$gender))),
selected = "All"
),
# Checkboxes for medications
checkboxGroupInput(
"medication_filter",
"Filter by Medications:",
choices = c(
"Metformin", "Repaglinide", "Nateglinide", "Chlorpropamide",
"Glimepiride", "Acetohexamide", "Glipizide", "Glyburide",
"Tolbutamide", "Pioglitazone", "Rosiglitazone", "Acarbose",
"Miglitol", "Troglitazone", "Tolazamide", "Examide",
"Sitagliptin", "Insulin", "Glyburide-Metformin",
"Glipizide-Metformin", "Glimepiride-Pioglitazone",
"Metformin-Rosiglitazone", "Metformin-Pioglitazone"
),
selected = NULL
)
),
mainPanel(
# Display a bar plot
plotOutput("readmissionPlot")
)) )
library(shiny)
server <- function(input, output) {
# Reactive data loading dataset <- reactive({ req(input\(data_file) # Ensure a file is uploaded load_data(input\)data_file$datapath) # Call the load_data function })
# Reactive filtering filtered_data <- reactive({ data <- dataset()
# Filter by readmission status
if (input$readmission_filter != "All") {
data <- data[data$Readmitted == input$readmission_filter, ]
}
# Filter by medications
if (!is.null(input$medication_filter)) {
for (med in input$medication_filter) {
if (med %in% colnames(data)) { # Only filter if column exists
data <- data[data[[med]] == 1, ]
} else {
warning(paste("Medication column", med, "not found in dataset"))
}
}
}
if (nrow(data) == 0) {
return(NULL) # Handle empty results gracefully
}
data})
# Render the bar plot output$readmissionPlot <- renderPlot({ data <- filtered_data() if (is.null(data)) { plot.new() text(0.5, 0.5, “No data to display after filtering”, cex = 1.5) return() }
# Count the number of patients by readmission status
readmission_counts <- table(data$Readmitted)
# Create a bar plot
barplot(
readmission_counts,
main = "Readmission Status",
ylab = "Number of Patients",
xlab = "Readmission",
col = c("skyblue", "orange", "lightgreen")
)}) }
quarto::quarto_render("01_load.qmd")[31m
processing file: 01_load.qmd
[39m
|
| | 0%
|
|...... | 11%
|
|............ | 22% [unnamed-chunk-1]
|
|................. | 33%
|
|....................... | 44% [unnamed-chunk-2]
|
|............................. | 56%
|
|................................... | 67% [unnamed-chunk-3][31mtrying URL 'https://archive.ics.uci.edu/ml/machine-learning-databases/00296/dataset_diabetes.zip'
[39m[31mdownloaded 3.2 MB
[39m
|
|........................................ | 78%
|
|.............................................. | 89% [unnamed-chunk-4][31mtrying URL 'https://www.cms.gov/medicare/coding/icd9providerdiagnosticcodes/downloads/icd-9-cm-v32-master-descriptions.zip'
[39m[31mContent type 'application/zip' length 1079497 bytes (1.0 MB)
[39m[31m==[39m[31m==[39m[31m=[39m[31m=[39m[31m==[39m[31m==[39m[31m=[39m[31m==[39m[31m==[39m[31m=[39m[31m==[39m[31m=[39m[31m=[39m[31m===[39m[31m=[39m[31m====[39m[31m===[39m[31m==[39m[31m======[39m[31m===[39m[31m==[39m[31m=[39m[31m===[39m[31m==
[39m[31mdownloaded 1.0 MB
[39m
|
|....................................................| 100%
[31moutput file: 01_load.knit.md
[39m[1mpandoc [22m
to: html
output-file: 01_load.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'Load: Group 03'
editor: visual
Output created: ../results/R/01_load.htmlquarto::quarto_render("02_clean.qmd")[31m
processing file: 02_clean.qmd
[39m
|
| | 0%
|
|... | 7%
|
|....... | 13% [unnamed-chunk-1]
|
|.......... | 20%
|
|.............. | 27% [unnamed-chunk-2]
|
|................. | 33%
|
|..................... | 40% [unnamed-chunk-3]
|
|........................ | 47%
|
|............................ | 53% [unnamed-chunk-4]
|
|............................... | 60%
|
|................................... | 67% [unnamed-chunk-5]
|
|...................................... | 73%
|
|.......................................... | 80% [unnamed-chunk-6]
|
|............................................. | 87%
|
|................................................. | 93% [unnamed-chunk-7]
|
|....................................................| 100%
[31moutput file: 02_clean.knit.md
[39m[1mpandoc [22m
to: html
output-file: 02_clean.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'Clean: Group 03'
editor: visual
Output created: ../results/R/02_clean.htmlquarto::quarto_render("03_augment.qmd")[31m
processing file: 03_augment.qmd
[39m
|
| | 0%
|
|..... | 9%
|
|......... | 18% [unnamed-chunk-1]
|
|.............. | 27%
|
|................... | 36% [unnamed-chunk-2]
|
|........................ | 45%
|
|............................ | 55% [unnamed-chunk-3]
|
|................................. | 64%
|
|...................................... | 73% [unnamed-chunk-4]
|
|........................................... | 82%
|
|............................................... | 91% [unnamed-chunk-5]
|
|....................................................| 100%
[31moutput file: 03_augment.knit.md
[39m[1mpandoc [22m
to: html
output-file: 03_augment.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'Augment: Group 03'
editor: visual
Output created: ../results/R/03_augment.htmlquarto::quarto_render("04_description.qmd")[31m
processing file: 04_description.qmd
[39m
|
| | 0%
|
|.. | 4%
|
|.... | 9% [unnamed-chunk-1]
|
|....... | 13%
|
|......... | 17% [unnamed-chunk-2]
|
|........... | 22%
|
|............. | 26% [unnamed-chunk-3]
|
|................ | 30%
|
|.................. | 35% [unnamed-chunk-4]
|
|.................... | 39%
|
|...................... | 43% [unnamed-chunk-5]
|
|........................ | 48%
|
|........................... | 52% [unnamed-chunk-6]
|
|............................. | 57%
|
|............................... | 61% [unnamed-chunk-7]
|
|................................. | 65%
|
|................................... | 70% [unnamed-chunk-8]
|
|...................................... | 74%
|
|........................................ | 78% [unnamed-chunk-9]
|
|.......................................... | 83%
|
|............................................ | 87% [unnamed-chunk-10]
|
|............................................... | 91%
|
|................................................. | 96% [unnamed-chunk-11]
|
|...................................................| 100%
[31moutput file: 04_description.knit.md
[39m[1mpandoc [22m
to: html
output-file: 04_description.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'Description: Group 03'
editor: visual
Output created: ../results/R/04_description.htmlquarto::quarto_render("05_visualizations.qmd")[31m
processing file: 05_visualizations.qmd
[39m
|
| | 0%
|
| | 3%
|
|. | 5% [unnamed-chunk-1]
|
|. | 8%
|
|. | 10% [unnamed-chunk-2]
|
|. | 13%
|
|.. | 15% [average_number_of_diagnoses_for_all]
|
|.. | 18%
|
|.. | 21% [average_diagnoses_for_all_races]
|
|.. | 23%
|
|... | 26% [race_gender_distribution]
|
|... | 28%
|
|... | 31% [discharge_disposition_for_all_admission_types]
|
|... | 33%
|
|.... | 36% [discharge_disposition_for_emergency_admissions]
|
|.... | 38%
|
|.... | 41% [discharge_disposition_for_urgent_admissions]
|
|.... | 44%
|
|..... | 46% [discharge_disposition_for_elective_admissions]
|
|..... | 49%
|
|..... | 51% [number_of_visits_per_patient]
|
|..... | 54%
|
|...... | 56% [diagnosis_for_1_visit]
|
|...... | 59%
|
|...... | 62% [diagnosis_for_2_visits]
|
|...... | 64%
|
|....... | 67% [diagnosis_for_3_visits]
|
|....... | 69%
|
|....... | 72% [average_number_of_diagnoses_per_visit_by_patient]
|
|....... | 74%
|
|........ | 77% [most_common_primary_diagnoses_per_visit]
|
|........ | 79%
|
|........ | 82% [unnamed-chunk-3]
|
|........ | 85%
|
|......... | 87% [unnamed-chunk-4]
|
|......... | 90%
|
|......... | 92% [diabetes_management_and_complications_for_all_patients]
|
|......... | 95%
|
|..........| 97% [diabetes_management_and_complications_for_patients_with_complications]
|
|..........| 100%
[31moutput file: 05_visualizations.knit.md
[39m[1mpandoc [22m
to: html
output-file: 05_visualizations.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'Visulizations: Group 03'
editor: visual
Output created: ../results/R/05_visualizations.htmlquarto::quarto_render("06_analysis_PCA.qmd")[31m
processing file: 06_analysis_PCA.qmd
[39m
|
| | 0%
|
|.. | 5%
|
|.... | 10% [unnamed-chunk-1]
|
|....... | 14%
|
|......... | 19% [pc_coordinate_plot]
|
|........... | 24%
|
|............. | 29% [unnamed-chunk-2]
|
|................ | 33%
|
|.................. | 38% [rotation_matrix_plot]
|
|.................... | 43%
|
|...................... | 48% [unnamed-chunk-3]
|
|......................... | 52%
|
|........................... | 57% [variance_plot]
|
|............................. | 62%
|
|............................... | 67% [unnamed-chunk-4]
|
|.................................. | 71%
|
|.................................... | 76% [unnamed-chunk-5]
|
|...................................... | 81%
|
|........................................ | 86% [unnamed-chunk-6]
|
|........................................... | 90%
|
|............................................. | 95% [unnamed-chunk-7]
|
|...............................................| 100%
[31moutput file: 06_analysis_PCA.knit.md
[39m[1mpandoc [22m
to: html
output-file: 06_analysis_PCA.html
standalone: true
embed-resources: true
section-divs: true
html-math-method: mathjax
wrap: none
default-image-extension: png
[1mmetadata[22m
document-css: false
link-citations: true
date-format: long
lang: en
title: 'PCA: Group 03'
editor: visual
Output created: ../results/R/06_analysis_PCA.html